在Python中将HTML表转换为CSV

pip install beautifulsoup4
pip install csv

from bs4 import BeautifulSoup
import csv

def html_to_csv(html):
    soup = BeautifulSoup(html, 'html.parser')
    table = soup.find('table')  # 找到HTML中的表格

    rows = table.find_all('tr')  # 找到表格中的所有行

    with open('output.csv', 'w', newline='') as csvfile:
        writer = csv.writer(csvfile)

        for row in rows:
            csv_row = []
            cells = row.find_all(['th', 'td'])  # 找到行中的所有单元格

            for cell in cells:
                csv_row.append(cell.get_text())  # 获取单元格的文本内容

            writer.writerow(csv_row)  # 将一行写入CSV文件

    print("转换完成，已保存为output.csv文件")

# 示例HTML表格
html = '''
<table>
  <tr>
    <th>姓名</th>
    <th>年龄</th>
    <th>性别</th>
  </tr>
  <tr>
    <td>张三</td>
    <td>20</td>
    <td>男</td>
  </tr>
  <tr>
    <td>李四</td>
    <td>25</td>
    <td>女</td>
  </tr>
</table>
'''

html_to_csv(html)